# Claude Sonnet 4.5 vs GPT-4o mini

> Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 25.4 on the Noometry Index. GPT-4o mini costs 23× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-5-vs-gpt-4o-mini
- Last updated: 2026-10-10
- Shared benchmarks: 38

## Summary

- They share 38 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 10 categories and GPT-4o mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Sonnet 4.5 leads 48.4 to 17.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Claude Sonnet 4.5 and 6.9% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Claude Sonnet 4.5 accepts more context: 1M tokens versus 128K.

## Snapshot

| | Claude Sonnet 4.5 | GPT-4o mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 44.0 | 25.4 |
| Rank | 76 | 337 |
| Context | 1M | 128K |
| Input $/M | $3 | $0.15 |
| Output $/M | $15 | $0.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4.5: 47.8 (#54)
- GPT-4o mini: 21.6 (#330)

| Benchmark | Claude Sonnet 4.5 | GPT-4o mini |
|---|---|---|
| WeirdML | 47.7% | 11.8% |
| LMArena Coding | 1489 | 1290 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| Aider Polyglot | — | 3.6% |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |

## Agentic & Tool Use

- Claude Sonnet 4.5: 38.1 (#30)
- GPT-4o mini: 27.2 (#95)

| Benchmark | Claude Sonnet 4.5 | GPT-4o mini |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| BALROG | — | 17.4% |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |

## Reasoning

- Claude Sonnet 4.5: 26.9 (#113)
- GPT-4o mini: 8.7 (#343)

| Benchmark | Claude Sonnet 4.5 | GPT-4o mini |
|---|---|---|
| ARC-AGI-2 | 13.6% | 0% |
| SimpleBench | 54.3% | 10.7% |
| Kagi LLM Benchmark | 57.9% | 28.8% |
| Chess Puzzles | 12% | 0% |
| LMArena Hard Prompts | 1462 | 1267 |
| Mystery Game Puzzles | 17% | 12% |
| DTBench | 83.2% | 54.4% |
| LMCA | 38.8% | 10.4% |
| Epoch Capabilities Index | 146.84 | 126.56 |
| NYT Connections (extended) | 37.3% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| LiveBench Reasoning | — | 32.8% |
| LiveBench Data Analysis | — | 50% |
| ForecastBench | 61.9 | — |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |

## Math

- Claude Sonnet 4.5: 31.9 (#190)
- GPT-4o mini: 9.9 (#307)

| Benchmark | Claude Sonnet 4.5 | GPT-4o mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 23.9% | 0.7% |
| OTIS Mock AIME 2024-2025 | 77.8% | 6.9% |
| Omni-MATH | 55.3% | 28% |
| LMArena Math | 1448 | 1267 |
| MATH Level 5 | 97.7% | 52.6% |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 19% | — |
| LiveBench Math | — | 36.3% |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 91.3% |

## Knowledge

- Claude Sonnet 4.5: 48.4 (#70)
- GPT-4o mini: 17.7 (#279)

| Benchmark | Claude Sonnet 4.5 | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 82.3% | 37.7% |
| SimpleQA Verified | 30.7% | 8.3% |
| MMLU-Pro | 86.9% | 60.3% |
| GPQA (HELM) | 68.6% | 36.8% |
| LMArena Expert | 1483 | 1235 |
| Humanity's Last Exam | 13.7% | — |
| Confabulations | — | 37.2% |
| Vectara Hallucination Rate | 12% | — |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |

## Multimodal

- Claude Sonnet 4.5: 34.1 (#84)
- GPT-4o mini: 25.3 (#117)

| Benchmark | Claude Sonnet 4.5 | GPT-4o mini |
|---|---|---|
| VPCT | 39.8% | 34% |
| LMArena Vision | — | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| LMArena Document | 1450 | — |

## Multilingual

- Claude Sonnet 4.5: 53.6 (#65)
- GPT-4o mini: 42.2 (#194)

| Benchmark | Claude Sonnet 4.5 | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1425 | 1266 |
| LMArena Chinese | 1459 | 1264 |
| LMArena French | 1459 | 1296 |
| LMArena German | 1427 | 1272 |
| LMArena Japanese | 1390 | 1216 |
| LMArena Korean | 1403 | 1195 |
| LMArena Russian | 1436 | 1275 |
| LMArena Spanish | 1457 | 1276 |

## Instruction Following

- Claude Sonnet 4.5: 75.2 (#74)
- GPT-4o mini: 62.1 (#234)

| Benchmark | Claude Sonnet 4.5 | GPT-4o mini |
|---|---|---|
| IFEval | 85% | 78.2% |
| LMArena Instruction Following | 1459 | 1259 |
| LiveBench Instruction Following | — | 56.8% |

## Long Context

- Claude Sonnet 4.5: 45.2 (#45)
- GPT-4o mini: 39.1 (#181)

| Benchmark | Claude Sonnet 4.5 | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1476 | 1289 |

## Writing & Preference

- Claude Sonnet 4.5: 66.7 (#33)
- GPT-4o mini: 39.7 (#243)

| Benchmark | Claude Sonnet 4.5 | GPT-4o mini |
|---|---|---|
| LMArena Text | 1439 | 1286 |
| LMArena Creative Writing | 1442 | 1268 |
| EQ-Bench Creative Writing | 1678 | 873 |
| WildBench | 85.4% | 79.1% |
| LMArena Multi-Turn | 1465 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| LiveBench Language | — | 28.6% |

## FAQ

### Is Claude Sonnet 4.5 better than GPT-4o mini?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 25.4 on the Noometry Index. GPT-4o mini costs 23× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 4.5 or GPT-4o mini?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

### Is Claude Sonnet 4.5 or GPT-4o mini better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.8 versus 21.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 4.5 does, with 1M tokens against 128K.

### How many benchmarks do Claude Sonnet 4.5 and GPT-4o mini share?

38 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and GPT-4o mini has 60.